# %%

# Load the required libraries

from participation_lib import (
    np,
    pd,
    plt,
    sns,
    load_data,
    get_stake_distribution,
    assign_commitee_plus,
    simulate,
    std_error,
    plot_group_to_committee_index,
    plot_selection_count_vs_stake,
    plot_committee_selection_counts,
    plot_committee_selection_seat_cutoff,
)

# %%

# Load the Data: The population of registered SPOs

population = load_data("../data/pooltool-cleaned.csv")

print(population.info())

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3056 entries, 0 to 3055
Data columns (total 3 columns):
 #   Column         Non-Null Count  Dtype  
---  ------         --------------  -----  
 0   id             3056 non-null   object 
 1   stake          3056 non-null   int64  
 2   stake_percent  3056 non-null   float64
dtypes: float64(1), int64(1), object(1)
memory usage: 71.8+ KB
None

# %%

population.describe()

# %%

# Let's now sample a group of participants from the population
# and calculate the stake weight for each participant.

group_size = 100

group_stakes = get_stake_distribution(
    population,
    group_size=group_size,
    num_iter=1000,
    plot_it=True,
)
print(group_stakes)

           stake  stake_weight
0   7.283987e+07  9.217518e-02
1   6.846427e+07  8.663808e-02
2   6.461900e+07  8.177208e-02
3   5.964222e+07  7.547422e-02
4   5.455957e+07  6.904238e-02
..           ...           ...
95  1.986700e+01  2.514069e-08
96  1.168200e+01  1.478298e-08
97  6.484000e+00  8.205175e-09
98  3.224000e+00  4.079809e-09
99  1.600000e+00  2.024719e-09

[100 rows x 2 columns]

# %%

print(group_stakes.describe())

              stake  stake_weight
count  1.000000e+02  1.000000e+02
mean   7.902330e+06  1.000000e-02
std    1.665953e+07  2.108180e-02
min    1.600000e+00  2.024719e-09
25%    1.837206e+03  2.324892e-06
50%    1.513475e+05  1.915227e-04
75%    4.831149e+06  6.113575e-03
max    7.283987e+07  9.217518e-02

# %%

# Let's now assign a committee of the fixed group_size
# based on the stake weight of each

results = assign_commitee_plus(
    group_stakes,
    committee_size=group_size,
    num_iter=1000,
)

# %%

# Let's now create a plots of committee assignments where we vary
# the group size over {100, 200, 300, 400, 500} and see how the
# committee selection and seat count changes.

# Initialize Parameters:
# comm_sizes = [100]  # vary over committee size, k
# group_sizes = [100]  # vary over group size, n
comm_sizes = [100, 200, 300, 400, 500]  # vary over committee size, k
group_sizes = [100, 200, 300, 400, 500]  # vary over group size, n
num_iter = 1  # Number of iterations for Monte Carlo simulation

# Note that the number of iterations here can be interpreted as the number
# of selection rounds for the committee, which we call an epoch.
# If we have a new epoch per day, then 1000 iterations is about 3 years.

# %%

# Call the function
sim_results_df = simulate(
    population,
    comm_sizes,
    group_sizes,
    num_iter,
    plot_it=True,
)

Committee Size = 100
Group Size = 100

Group Size = 200

Group Size = 300

Group Size = 400

Group Size = 500

Committee Size = 200
Group Size = 100

Group Size = 200

Group Size = 300

Group Size = 400

Group Size = 500

# %%

# committee_seats_df = committee_seats_df.swaplevel(axis=1).sort_index(axis=1)

# %%

# Extract the data for plotting

col_index = sim_results_df.columns
commitee_sizes = [
    int(col.split("=")[1].strip()) for col in col_index.get_level_values(0).unique()
]
group_sizes = [
    int(col.split("=")[1].strip()) for col in col_index.get_level_values(1).unique()
]

# %%

# Plot the percentage of group participants excluded from a committee
# of a given size vs. different group sizes

fig, ax = plt.subplots(figsize=(12, 8))

sns.set(style="whitegrid")

for committee_size in commitee_sizes:
    committee_label = f"Committee Size = {committee_size}"
    committee_voters = sim_results_df.loc["Distinct Voters", committee_label]

    mean_values = committee_voters.loc["mean"]
    std_dev_values = committee_voters.loc["sd"]

    # Calculate the percentage of participants not selected for committee seats
    not_selected_percentages = (1.0 - mean_values / group_sizes) * 100
    not_selected_percentages.name = "Excluded (%)"

    # Create a DataFrame for easier plotting with seaborn
    plot_data = pd.DataFrame(
        {
            "Group Size": group_sizes,
            "Percentage Excluded": not_selected_percentages,
            "Std Dev": std_dev_values,
        }
    )

    # Plot the main line without error bars
    sns.lineplot(
        x="Group Size",
        y="Percentage Excluded",
        data=plot_data,
        marker="o",
        label=committee_label,
        ax=ax,
    )

ax.set_ylabel("Percentage Excluded")
ax.set_xlabel("Group Size")
ax.legend(title="Committee Size")
plt.title("Percentage of Group Participants Not Selected for Committee Seats")
plt.grid(True)
plt.show()

# %%

sim_results_df.loc["Distinct Voters", :]

# %%

# Plot the committee selection counts distribution
fig = plt.figure(figsize=(12, 8))

plot_data = sim_results_df.loc["Committee Seats"].loc["mean"]

for c, g in plot_data.index:

    y = plot_data.loc[(c, g)]
    x = y.index

    n_c = int(c.split("=")[1].strip())
    n_g = int(g.split("=")[1].strip())

    colors = sns.color_palette("tab20", len(plot_data.index))
    color_idx = list(plot_data.index).index((c, g))
    plt.bar(x, y, alpha=0.7, color=colors[color_idx], label=f"{n_c}, {n_g}")

plt.xlabel("Participant Index")
plt.ylabel("Committee Seat Count (average)")
plt.title("Committee Seat Count for Participants")
plt.legend(title="Committee Size, Group Size")
plt.xlim(0, 200)
plt.show()

# %%

# Distinct Voters
committee_voters = sim_results_df.loc["Distinct Voters"]

# Create a DataFrame row from the computed percentages
mean_values = committee_voters.loc["mean"]
std_dev_values = committee_voters.loc["sd"]

# Calculate the percentage of participants not selected for committee seats
print("Percentage of Group Participants Not Selected for Committee Seats:")
committee_participation = pd.concat([mean_values, std_dev_values], axis=1)
# committee_participation.columns = ["Mean", "Std Dev"]

print(committee_participation)

Percentage of Group Participants Not Selected for Committee Seats:
                                        mean   sd
Committee Size       Group Size                  
Committee Size = 100 Group Size = 100   25.0  0.0
                     Group Size = 200   37.0  0.0
                     Group Size = 300   50.0  0.0
                     Group Size = 400   52.0  0.0
                     Group Size = 500   58.0  0.0
Committee Size = 200 Group Size = 100   31.0  0.0
                     Group Size = 200   51.0  0.0
                     Group Size = 300   71.0  0.0
                     Group Size = 400   81.0  0.0
                     Group Size = 500   91.0  0.0
Committee Size = 300 Group Size = 100   40.0  0.0
                     Group Size = 200   45.0  0.0
                     Group Size = 300   76.0  0.0
                     Group Size = 400   91.0  0.0
                     Group Size = 500  109.0  0.0
Committee Size = 400 Group Size = 100   35.0  0.0
                     Group Size = 200   66.0  0.0
                     Group Size = 300   85.0  0.0
                     Group Size = 400   95.0  0.0
                     Group Size = 500  103.0  0.0
Committee Size = 500 Group Size = 100   39.0  0.0
                     Group Size = 200   68.0  0.0
                     Group Size = 300   76.0  0.0
                     Group Size = 400  121.0  0.0
                     Group Size = 500  123.0  0.0

# %%

# Prepare the DataFrame for concatenation with the other simulation results
committee_participation = committee_participation.T
committee_participation.index = pd.MultiIndex.from_tuples(
    [("Committee Participation %", "mean"), ("Committee Participation %", "sd")]
)

# Concatenate this new row to the simulation results DataFrame
sim_results_df = pd.concat([sim_results_df, committee_participation], axis=0)

sim_results_df

# %%

# Let's now create a plots of committee assignments where we vary
# the group size over {100, 200, 300, 400, 500} and see how the
# committee selection and seat count changes.

# Initialize Parameters:
# comm_sizes = [100]  # vary over committee size, k
# group_sizes = [100]  # vary over group size, n
comm_sizes = [100, 200, 300, 400, 500]  # vary over committee size, k
group_sizes = [100, 200, 300, 400, 500]  # vary over group size, n
num_iter = 30  # Number of iterations for Monte Carlo simulation

# Note that the number of iterations here can be interpreted as the number
# of selection rounds for the committee, which we call an epoch.
# If we have a new epoch per day, then 1000 iterations is about 3 years.

# %%

# Call the function
sim_results_df = simulate(
    population,
    comm_sizes,
    group_sizes,
    num_iter,
    plot_it=True,
)

Committee Size = 100
Group Size = 100

Group Size = 200

Group Size = 300

Group Size = 400

Group Size = 500

Committee Size = 200
Group Size = 100

Group Size = 200

Group Size = 300

Group Size = 400

Group Size = 500

# %%

# committee_seats_df = committee_seats_df.swaplevel(axis=1).sort_index(axis=1)

# %%

# Extract the data for plotting

col_index = sim_results_df.columns
commitee_sizes = [
    int(col.split("=")[1].strip()) for col in col_index.get_level_values(0).unique()
]
group_sizes = [
    int(col.split("=")[1].strip()) for col in col_index.get_level_values(1).unique()
]

# %%

# Plot the percentage of group participants excluded from a committee
# of a given size vs. different group sizes

fig, ax = plt.subplots(figsize=(12, 8))

sns.set(style="whitegrid")

for committee_size in commitee_sizes:
    committee_label = f"Committee Size = {committee_size}"
    committee_voters = sim_results_df.loc["Distinct Voters", committee_label]

    mean_values = committee_voters.loc["mean"]
    std_dev_values = committee_voters.loc["sd"]

    # Calculate the percentage of participants not selected for committee seats
    not_selected_percentages = (1.0 - mean_values / group_sizes) * 100
    not_selected_percentages.name = "Excluded (%)"

    # Create a DataFrame for easier plotting with seaborn
    plot_data = pd.DataFrame(
        {
            "Group Size": group_sizes,
            "Percentage Excluded": not_selected_percentages,
            "Std Dev": std_dev_values,
        }
    )

    # Plot the main line without error bars
    sns.lineplot(
        x="Group Size",
        y="Percentage Excluded",
        data=plot_data,
        marker="o",
        label=committee_label,
        ax=ax,
    )

ax.set_ylabel("Percentage Excluded")
ax.set_xlabel("Group Size")
ax.legend(title="Committee Size")
plt.title("Percentage of Group Participants Not Selected for Committee Seats")
plt.grid(True)
plt.show()

# %%

sim_results_df.loc["Distinct Voters", :]

# %%

# Plot the committee selection counts distribution
fig = plt.figure(figsize=(12, 8))

plot_data = sim_results_df.loc["Committee Seats"].loc["mean"]

for c, g in plot_data.index:

    y = plot_data.loc[(c, g)]
    x = y.index

    n_c = int(c.split("=")[1].strip())
    n_g = int(g.split("=")[1].strip())

    colors = sns.color_palette("tab20", len(plot_data.index))
    color_idx = list(plot_data.index).index((c, g))
    plt.bar(x, y, alpha=0.7, color=colors[color_idx], label=f"{n_c}, {n_g}")

plt.xlabel("Participant Index")
plt.ylabel("Committee Seat Count (average)")
plt.title("Committee Seat Count for Participants")
plt.legend(title="Committee Size, Group Size")
plt.xlim(0, 200)
plt.show()

# %%

# Distinct Voters
committee_voters = sim_results_df.loc["Distinct Voters"]

# Create a DataFrame row from the computed percentages
mean_values = committee_voters.loc["mean"]
std_dev_values = committee_voters.loc["sd"]

# Calculate the percentage of participants not selected for committee seats
print("Percentage of Group Participants Not Selected for Committee Seats:")
committee_participation = pd.concat([mean_values, std_dev_values], axis=1)
# committee_participation.columns = ["Mean", "Std Dev"]

print(committee_participation)

Percentage of Group Participants Not Selected for Committee Seats:
                                             mean        sd
Committee Size       Group Size                            
Committee Size = 100 Group Size = 100   25.466667  2.692376
                     Group Size = 200        40.6  2.332381
                     Group Size = 300        50.5  2.459675
                     Group Size = 400        57.2  3.673327
                     Group Size = 500   63.733333  3.604935
Committee Size = 200 Group Size = 100   31.366667  2.316367
                     Group Size = 200        50.9  2.785079
                     Group Size = 300   66.966667   3.25047
                     Group Size = 400   79.133333  4.514667
                     Group Size = 500   91.133333  4.709801
Committee Size = 300 Group Size = 100        33.2  2.181742
                     Group Size = 200   57.033333   3.25047
                     Group Size = 300        75.5  3.442383
                     Group Size = 400   90.666667  3.486482
                     Group Size = 500       108.1  5.127377
Committee Size = 400 Group Size = 100        37.2   1.83303
                     Group Size = 200   61.566667   3.58407
                     Group Size = 300   81.166667  3.387067
                     Group Size = 400   99.766667  4.038839
                     Group Size = 500  118.466667   4.68852
Committee Size = 500 Group Size = 100        37.8  2.181742
                     Group Size = 200   62.766667  3.018646
                     Group Size = 300   86.466667  2.629744
                     Group Size = 400  108.366667  4.370228
                     Group Size = 500  125.966667  5.552677

# %%

# Prepare the DataFrame for concatenation with the other simulation results
committee_participation = committee_participation.T
committee_participation.index = pd.MultiIndex.from_tuples(
    [("Committee Participation %", "mean"), ("Committee Participation %", "sd")]
)

# Concatenate this new row to the simulation results DataFrame
sim_results_df = pd.concat([sim_results_df, committee_participation], axis=0)

sim_results_df

# %%

# Save the results to an Excel file
output_file = "../data/participation_run_results.xlsx"
sim_results_df.to_excel(output_file)
print(f"Results saved to {output_file}")

Results saved to ../data/participation_run_results.xlsx

	stake	stake_percent
count	3.056000e+03	3056.000000
mean	7.305314e+06	0.032723
std	1.648449e+07	0.073839
min	0.000000e+00	0.000000
25%	5.265000e+02	0.000002
50%	5.692500e+04	0.000255
75%	3.282500e+06	0.014703
max	1.054300e+08	0.472250

Participation Distribution in Committee Selection¶

Executive Summary¶

Committee Size	Committee Size = 100					Committee Size = 200					...	Committee Size = 400					Committee Size = 500
Group Size	Group Size = 100	Group Size = 200	Group Size = 300	Group Size = 400	Group Size = 500	Group Size = 100	Group Size = 200	Group Size = 300	Group Size = 400	Group Size = 500	...	Group Size = 100	Group Size = 200	Group Size = 300	Group Size = 400	Group Size = 500	Group Size = 100	Group Size = 200	Group Size = 300	Group Size = 400	Group Size = 500
mean	25.0	37.0	50.0	52.0	58.0	31.0	51.0	71.0	81.0	91.0	...	35.0	66.0	85.0	95.0	103.0	39.0	68.0	76.0	121.0	123.0
sd	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0